Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2936 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7772. Min Range: -6.7772
Max Act: 6.7772. Min Act: -0.1700
Data Index: 1195303 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7772. Min Range: -6.7772
Max Act: 6.6522. Min Act: -0.1700
Data Index: 2828526 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7772. Min Range: -6.7772
Max Act: 6.6522. Min Act: -0.1700
Data Index: 1204755 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7772. Min Range: -6.7772
Max Act: 6.5272. Min Act: -0.1700
Data Index: 1916917 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7772. Min Range: -6.7772
Max Act: 6.5272. Min Act: -0.1700
Data Index: 8285723 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7772. Min Range: -6.7772
Max Act: 6.4959. Min Act: -0.1700
Data Index: 858284 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7772. Min Range: -6.7772
Max Act: 6.4959. Min Act: -0.1700
Data Index: 4040185 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7772. Min Range: -6.7772
Max Act: 6.4334. Min Act: -0.1700
Data Index: 2344974 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7772. Min Range: -6.7772
Max Act: 6.4022. Min Act: -0.1700
Data Index: 5228366 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7772. Min Range: -6.7772
Max Act: 6.4022. Min Act: -0.1700
Data Index: 6970977 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7772. Min Range: -6.7772
Max Act: 6.4022. Min Act: -0.1700
Data Index: 1582253 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7772. Min Range: -6.7772
Max Act: 6.4022. Min Act: -0.1700
Data Index: 5233995 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7772. Min Range: -6.7772
Max Act: 6.3709. Min Act: -0.1700
Data Index: 3787587 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7772. Min Range: -6.7772
Max Act: 6.3397. Min Act: -0.1700
Data Index: 5599986 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7772. Min Range: -6.7772
Max Act: 6.3084. Min Act: -0.1700
Data Index: 7817261 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7772. Min Range: -6.7772
Max Act: 6.3084. Min Act: -0.1700
Data Index: 696859 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7772. Min Range: -6.7772
Max Act: 6.3397. Min Act: -0.1700
Data Index: 7195424 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7772. Min Range: -6.7772
Max Act: 6.2459. Min Act: -0.1700
Data Index: 1356070 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7772. Min Range: -6.7772
Max Act: 6.2772. Min Act: -0.1700
Data Index: 8033933 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7772. Min Range: -6.7772
Max Act: 6.2459. Min Act: -0.1700
Data Index: 7812618 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19